Compare commits

..

No commits in common. "984f9233c49ce99c2d754c143b95ce5674e3121f" and "2410edc0015a444f8bf68896e2c62337df2a1f29" have entirely different histories.

6 changed files with 26 additions and 77 deletions

View File

@ -481,7 +481,7 @@ class TestTraversalHelpers:
'id': 'name', 'id': 'name',
'data': 'content', 'data': 'content',
'url': 'url', 'url': 'url',
}, all, {subs_list_to_dict(lang=None)}]) == { }, all, {subs_list_to_dict}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}], 'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [{'data': 'content'}], 'en': [{'data': 'content'}],
}, 'subs with mandatory items missing should be filtered' }, 'subs with mandatory items missing should be filtered'
@ -507,54 +507,6 @@ class TestTraversalHelpers:
{'url': 'https://example.com/subs/en1', 'ext': 'ext'}, {'url': 'https://example.com/subs/en1', 'ext': 'ext'},
{'url': 'https://example.com/subs/en2', 'ext': 'ext'}, {'url': 'https://example.com/subs/en2', 'ext': 'ext'},
]}, '`quality` key should sort subtitle list accordingly' ]}, '`quality` key should sort subtitle list accordingly'
assert traverse_obj([
{'name': 'de', 'url': 'https://example.com/subs/de.ass'},
{'name': 'de'},
{'name': 'en', 'content': 'content'},
{'url': 'https://example.com/subs/en'},
], [..., {
'id': 'name',
'url': 'url',
'data': 'content',
}, all, {subs_list_to_dict(lang='en')}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [
{'data': 'content'},
{'url': 'https://example.com/subs/en'},
],
}, 'optionally provided lang should be used if no id available'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang=None)}]) == {
'de': [
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be ignored for id and ext'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang='de')}]) == {
'de': [
{'url': 'https://example.com/subs/de1'},
{'url': 'https://example.com/subs/de2'},
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be replaced by default id'
def test_trim_str(self): def test_trim_str(self):
with pytest.raises(TypeError): with pytest.raises(TypeError):
@ -573,7 +525,7 @@ class TestTraversalHelpers:
def test_unpack(self): def test_unpack(self):
assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123' assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3' assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3' assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3'
with pytest.raises(TypeError): with pytest.raises(TypeError):
unpack(join_nonempty)() unpack(join_nonempty)()
with pytest.raises(TypeError): with pytest.raises(TypeError):

View File

@ -72,6 +72,7 @@ from yt_dlp.utils import (
intlist_to_bytes, intlist_to_bytes,
iri_to_uri, iri_to_uri,
is_html, is_html,
join_nonempty,
js_to_json, js_to_json,
limit_length, limit_length,
locked_file, locked_file,
@ -2157,6 +2158,10 @@ Line 1
assert int_or_none(v=10) == 10, 'keyword passed positional should call function' assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function' assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially'
assert callable(join_nonempty()), 'varargs positional should apply partially'
assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function'
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

View File

@ -3767,7 +3767,7 @@ class InfoExtractor:
""" Merge subtitle dictionaries, language by language. """ """ Merge subtitle dictionaries, language by language. """
if target is None: if target is None:
target = {} target = {}
for d in filter(None, dicts): for d in dicts:
for lang, subs in d.items(): for lang, subs in d.items():
target[lang] = cls._merge_subtitle_items(target.get(lang, []), subs) target[lang] = cls._merge_subtitle_items(target.get(lang, []), subs)
return target return target

View File

@ -13,10 +13,7 @@ from ..utils import (
unified_timestamp, unified_timestamp,
url_or_none, url_or_none,
) )
from ..utils.traversal import ( from ..utils.traversal import traverse_obj
subs_list_to_dict,
traverse_obj,
)
class RutubeBaseIE(InfoExtractor): class RutubeBaseIE(InfoExtractor):
@ -95,11 +92,11 @@ class RutubeBaseIE(InfoExtractor):
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls') hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
formats.extend(fmts) formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles) self._merge_subtitles(subs, target=subtitles)
self._merge_subtitles(traverse_obj(options, ('captions', ..., { for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
'id': 'code', subtitles.setdefault(caption.get('code') or 'ru', []).append({
'url': 'file', 'url': caption['file'],
'name': ('langTitle', {str}), 'name': caption.get('langTitle'),
}, all, {subs_list_to_dict(lang='ru')})), target=subtitles) })
return formats, subtitles return formats, subtitles
def _download_and_extract_formats_and_subtitles(self, video_id, query=None): def _download_and_extract_formats_and_subtitles(self, video_id, query=None):

View File

@ -216,7 +216,7 @@ def partial_application(func):
sig = inspect.signature(func) sig = inspect.signature(func)
required_args = [ required_args = [
param.name for param in sig.parameters.values() param.name for param in sig.parameters.values()
if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD) if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL)
if param.default is inspect.Parameter.empty if param.default is inspect.Parameter.empty
] ]
@ -4837,6 +4837,7 @@ def number_of_digits(number):
return len('%d' % number) return len('%d' % number)
@partial_application
def join_nonempty(*values, delim='-', from_dict=None): def join_nonempty(*values, delim='-', from_dict=None):
if from_dict is not None: if from_dict is not None:
values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values) values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values)

View File

@ -332,14 +332,14 @@ class _RequiredError(ExtractorError):
@typing.overload @typing.overload
def subs_list_to_dict(*, lang: str | None = 'und', ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ... def subs_list_to_dict(*, ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
@typing.overload @typing.overload
def subs_list_to_dict(subs: list[dict] | None, /, *, lang: str | None = 'und', ext: str | None = None) -> dict[str, list[dict]]: ... def subs_list_to_dict(subs: list[dict] | None, /, *, ext: str | None = None) -> dict[str, list[dict]]: ...
def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None): def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
""" """
Convert subtitles from a traversal into a subtitle dict. Convert subtitles from a traversal into a subtitle dict.
The path should have an `all` immediately before this function. The path should have an `all` immediately before this function.
@ -352,7 +352,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
`quality` The sort order for each subtitle `quality` The sort order for each subtitle
""" """
if subs is None: if subs is None:
return functools.partial(subs_list_to_dict, lang=lang, ext=ext) return functools.partial(subs_list_to_dict, ext=ext)
result = collections.defaultdict(list) result = collections.defaultdict(list)
@ -360,15 +360,9 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
if not url_or_none(sub.get('url')) and not sub.get('data'): if not url_or_none(sub.get('url')) and not sub.get('data'):
continue continue
sub_id = sub.pop('id', None) sub_id = sub.pop('id', None)
if not isinstance(sub_id, str): if sub_id is None:
if not lang:
continue continue
sub_id = lang if ext is not None and not sub.get('ext'):
sub_ext = sub.get('ext')
if not isinstance(sub_ext, str):
if not ext:
sub.pop('ext', None)
else:
sub['ext'] = ext sub['ext'] = ext
result[sub_id].append(sub) result[sub_id].append(sub)
result = dict(result) result = dict(result)
@ -458,9 +452,9 @@ def trim_str(*, start=None, end=None):
return trim return trim
def unpack(func, **kwargs): def unpack(func):
@functools.wraps(func) @functools.wraps(func)
def inner(items): def inner(items, **kwargs):
return func(*items, **kwargs) return func(*items, **kwargs)
return inner return inner